-
Showcasing White-Box Implementation of the RSA Digital Signature Scheme
Colin Chibaya,
Mfundo Monchwe,
Taryn Nicole Michael,
Eli Bila Nimy
Issue:
Volume 5, Issue 4, December 2022
Pages:
198-203
Received:
30 July 2022
Accepted:
15 August 2022
Published:
18 October 2022
DOI:
10.11648/j.ajcst.20220504.11
Downloads:
Views:
Abstract: Data security is a priority in online transactions. Data security, in this context, refers to both data confidentiality, data integrity, and data authenticity when online transactions are completed. While a lot has been done to tighten data confidentiality, algorithms to address data integrity and data authenticity are rare. The RSA digital signature scheme dominates and is often connoted when data integrity and data authenticity problems are tabled. However, the original RSA digital signature scheme is not easy to comprehend by layman. Most component units of the RSA digital signature scheme require further clarity to facilitate reproducibility and hence productivity. This study showcases the implementation of a white-box RSA digital signature scheme. In this context, a digital signature is a computational algorithm used to ensure data confidentiality, integrity, and authenticity after online transactions. It is an algorithm that ensures that data is safe, has not been tampered with, and the claimed sender is truly the sender. We build the proposed implementation from an understanding that the RSA digital signature scheme is an asymmetric model which uses two keys. One key is used to sign data such that it can only be verified using the second key. A quantitative research approach was followed in which the effectiveness of the white-box RSA digital signature scheme was evaluated with respect to the execution time and signature verification accuracy. Execution time was assessed for different values of p, q, and data lengths. Similarly, verification accuracy was also assessed with different values of p, q, and data lengths. A tradeoff between security and execution time was noted as apparent. Low accuracy was observed when the values of p and q are small. Thus, big values of p and q are recommended for better data security.
Abstract: Data security is a priority in online transactions. Data security, in this context, refers to both data confidentiality, data integrity, and data authenticity when online transactions are completed. While a lot has been done to tighten data confidentiality, algorithms to address data integrity and data authenticity are rare. The RSA digital signatu...
Show More
-
Automatic Classification of Computing Literatures via Article and Reference Correlation
Oluwafemi Oriola,
Lawrence Ojo,
Ojonoka Atawodi
Issue:
Volume 5, Issue 4, December 2022
Pages:
204-209
Received:
17 September 2022
Accepted:
29 September 2022
Published:
21 October 2022
DOI:
10.11648/j.ajcst.20220504.12
Downloads:
Views:
Abstract: Automatic literature classification via machine learning has witnessed increasing attention in various research circles, especially computing community because of the availability of large body of research articles in diverse fields. Existing works have largely drawn features from segments of articles such as abstracts, contents and their metadata with little or no attention for references. This paper posited that correlating article and reference features would enhance the performance of machine learning algorithms. Therefore, we exploited the correlation of TFIDF of articles and references using association rule and cosine similarity-based correlation methods for classification of computing literatures. We focused on Adekunle Ajasin University Research Repository. Based on the ACM’s and Denning’s taxonomies, the research articles in the database were labelled by experienced computing professionals. Logistic Regression, Support Vector Machine and Multilayer Perceptron Neural Network with N-Gram features were explored as classifiers. For ACM’s taxonomy, the highest accuracy and F1-score of 0.56 and 0.41, respectively were obtained for association rule-based correlation; 0.62 and 0.51, respectively for similarity-based correlation; and 0.59 and 0.46, respectively for the existing article-based classification. For Denning’s taxonomy, the highest accuracy and F1-score of 0.41 and 0.40, respectively were obtained for association rule-based correlation; 0.41 and 0.36, respectively for similarity-based correlation; and 0.38 and 0.37, respectively for the existing article-based classification. These results show that both methods of correlation have better prospect than the popular abstract-based classification method in automatic classification of computing literatures.
Abstract: Automatic literature classification via machine learning has witnessed increasing attention in various research circles, especially computing community because of the availability of large body of research articles in diverse fields. Existing works have largely drawn features from segments of articles such as abstracts, contents and their metadata ...
Show More
-
Chromosome Segmentation Analysis Using Image Processing Techniques and Autoencoders
Amritha Pallavoor,
Prajwal Anagani,
Sundareshan Tambarahalli,
Sreekanth Pallavoor
Issue:
Volume 5, Issue 4, December 2022
Pages:
210-216
Received:
14 October 2022
Accepted:
10 November 2022
Published:
23 November 2022
DOI:
10.11648/j.ajcst.20220504.13
Downloads:
Views:
Abstract: Chromosome analysis and identification from metaphase images is a critical part of cytogenetics based medical diagnosis. It is mainly used for identifying constitutional, prenatal and acquired abnormalities in the diagnosis of genetic diseases and disorders. The process of identification of chromosomes from metaphase is a tedious one and requires trained personnel and several hours to perform. Challenge exists especially in handling touching, overlapping and clustered chromosomes in metaphase images, which if not segmented properly would result in wrong classification. This study proposes a method to automate the process of detection and segmentation of chromosomes from a given metaphase image, and in using them to classify through a Deep CNN architecture to know the chromosome type. There are two methods to handle the separation of overlapping chromosomes found in metaphases - one method involving watershed algorithm followed by autoencoders and the other a method purely based on watershed algorithm. These methods involve a combination of automation and very minimal manual effort to perform the segmentation, which produces the output. The manual effort ensures that human intuition is taken into consideration, especially in handling touching, overlapping and cluster chromosomes. Upon segmentation, individual chromo- some images are then classified into their respective classes with 95.75% accuracy using a Deep CNN model. Further, a distribution strategy is imparted to classify these chromosomes from the given output (which typically could consist of 46 individual images in a normal scenario for human beings) into its individual classes with an accuracy of 98%. This study helps conclude that pure manual effort involved in chromosome segmentation can be automated to a very good level through image processing techniques to produce reliable and satisfying results.
Abstract: Chromosome analysis and identification from metaphase images is a critical part of cytogenetics based medical diagnosis. It is mainly used for identifying constitutional, prenatal and acquired abnormalities in the diagnosis of genetic diseases and disorders. The process of identification of chromosomes from metaphase is a tedious one and requires t...
Show More
-
Development of a Model for Student-Lecturer Rating System
Akinbohun Folake,
Akinbohun Opeyemi Samuel,
Daodu Babalola Julius,
Ologunagba Grace Feyikemi
Issue:
Volume 5, Issue 4, December 2022
Pages:
217-221
Received:
13 November 2022
Accepted:
15 December 2022
Published:
27 December 2022
DOI:
10.11648/j.ajcst.20220504.14
Downloads:
Views:
Abstract: A Student-Lecturer Rating System is the rating of the lecturers by the students where factors like level of class interaction, classroom cooperation, frequency of meeting, teaching effectiveness, punctuality and open communication etc are considered as rating factors. Evaluation of lecturer’s performance usually faces challenges such as unfairness, imprecise and subjectivity in the area of allotting marks to lecturers. Another problem is the issue of information supplied by the lecturers that might not be one hundred percent true due to some typographical errors; it is often difficult to quantify performance dimensions, hence there is need to develop a model for rating lecturers by their students. The objective of this paper is to develop a model for student-lecturer rating system. The proposed system is based on using some variables which represent the rating factors which are evaluated using the models and using the aggregates are computed. On the basis of the aggregates, the rating factors are ranked. This system can be adopted to complement the existing system. The proposed model can be used where the students have the capacity to rate their lecturers on the basis of the rating factors. The lecturers with the high rated values can be promoted to the next level while the lecturers with low rated values are not qualified for promotion. If this can be adopted in the institutions, lecturers would like to add high rating factors to their values and to their work.
Abstract: A Student-Lecturer Rating System is the rating of the lecturers by the students where factors like level of class interaction, classroom cooperation, frequency of meeting, teaching effectiveness, punctuality and open communication etc are considered as rating factors. Evaluation of lecturer’s performance usually faces challenges such as unfairness,...
Show More
-
Enhancing Exercise Performance Through Heart Rate Zone Monitoring in Exergaming
Khasnur Abd Malek,
Mazapuspavina Md-Yasin,
Ilham Ameera Ismail,
Zahirah Tharek,
Nik Munirah Nik Mohd Nasir,
Hashbullah Ismail,
Mohamad Nahar Azmi Mohamed,
Mohamed Fareq Malek,
Hock Chuan Lim
Issue:
Volume 5, Issue 4, December 2022
Pages:
222-228
Received:
30 November 2022
Accepted:
19 December 2022
Published:
29 December 2022
DOI:
10.11648/j.ajcst.20220504.15
Downloads:
Views:
Abstract: Exercise performance helps to improve healthcare of the general public. It is important to create a fun environment to exercise as this will encourage people to maintain their effort to keep healthy and fit. The focus of this paper is to highlight a blueprint work which focuses on the initiative to improve exercise performance in current exergame innovation. This expert-driven work involved a collaborative initiative from four faculties of various disciplines as well as ICT experts from other universities. This is an important strategy as we intend to create effective and practical techniques to address the needs of the users' end who are the patients. The work evolved around the concept of measurement and monitoring of real-time heart rate zone to target exercise intensity during exergame sessions. The work also aims to provide people with the ease and simplicity to monitor their real-time exercise performance based on heart rate zone through mobile exergaming. Findings from this project suggest the importance of improving exercise via exergame for example, effective performance during exergaming sessions, in the long run, is critical for a positive impact on health. This work can form a basis for a community-wide approach to address the major public health problem of non-communicable disease from physical inactivity.
Abstract: Exercise performance helps to improve healthcare of the general public. It is important to create a fun environment to exercise as this will encourage people to maintain their effort to keep healthy and fit. The focus of this paper is to highlight a blueprint work which focuses on the initiative to improve exercise performance in current exergame i...
Show More
